IEEE

DeepU-Net: A Parallel Dual-Branch Model for Deeply Fusing Multiscale Features for Road Extraction From High-Resolution Remote Sensing Images

Abstract: The existing encoder–decoder model, or encoder–decoder model with atrous convolutions, has exposed its limitations under diverse environments, such as road scales, shadows, building ...
IEEE

FastSAM-CD: Remote Sensing Image Change Detection Using Vision Foundation Models With Stronger Encoder and Decoder

Abstract: Remote sensing image change detection (RSICD) is a crucial technique for Earth observation. However, the mainstream RSICD methods still face two main challenges. First, the encoding stage ...
GitHub

vLLM BART Model Plugin

BART is an encoder-decoder model that is particularly effective for sequence-to-sequence tasks like summarization, translation, and text generation. Florence-2 is a vision-language model from ...
Microsoft

Paza: Introducing automatic speech recognition benchmarks and models for low resource languages

According to the 2025 Microsoft AI Diffusion Report approximately one in six people globally had used a generative AI product. Yet for billions of people, the promise of voice interaction still falls ...